Topic
Image conversion
About: Image conversion is a research topic. Over the lifetime, 2490 publications have been published within this topic receiving 19077 citations.
Papers published on a yearly basis
Papers
More filters
Patent•
21 Jul 2005
TL;DR: In this paper, a dynamic image conversion processor is proposed to convert a high frame rate animation into one that can be MPEG-processed while suppressing subjective deterioration in image quality by dividing the input dynamic image into blocks and applying image conversion processing utilizing an ultra-resolution to each of the divided blocks.
Abstract: PROBLEM TO BE SOLVED: To enable allowing a frame rate into one that can be MPEG-processed while suppressing subjective deterioration in image quality. SOLUTION: An animation of high frame rate (e.g. 240 fps) which cannot be processed in MPEG is inputted into a dynamic image conversion processor 21. The processor 21 divides the inputted dynamic image into blocks, applies image conversion processing utilizing an ultra-resolution to each of the divided blocks, and converts the inputted dynamic image. A dynamic image conversion processor 11 supplies the blocks of a dynamic image of a frame rate (60 fps) which can be processed in MPEG to an output section 22. An output section 22 converts the frame rate of the dynamic image processed by the section 21 into 1/M (M being natural number) to form it into a frame rate which can be processed in MPEG, and supplies it to a coding section 12. For example, an input frame rate of 240 fps is made into 60 fps which can be finally subjected to MPEG, that means, the frame rate is reduced into 1/4. COPYRIGHT: (C)2005,JPO&NCIPI
5 citations
Patent•
24 Nov 2017
TL;DR: In this article, an image stylization method is executed based on a trained first network, which includes the following steps that: a first image is acquired; the first image was inputted to the first network; and the second network was utilized to perform stylization processing on a second image to be processed, so that a third image corresponding to the second image was obtained.
Abstract: The invention discloses an image stylization processing method, an image stylization processing device, a computing apparatus and a computer storage medium The image stylization processing method is executed based on a trained first network The method includes the following steps that: a first image is acquired; the first image is inputted to the first network, so that a second network corresponding to the style of the first image is obtained; and the second network is utilized to perform stylization processing on a second image to be processed, so that a third image corresponding to the second image is obtained According to the image stylization processing method provided by the technical schemes of the present invention, the corresponding image conversion network can be quickly obtained by using the trained first network, and therefore, the efficiency of image stylization processing is improved, and an image stylization processing mode is optimized
5 citations
Patent•
29 Sep 2000
TL;DR: In this paper, an image processor is provided with an area sensor 6 that reads image information from a negative film, an area extract section 23 that extracts the face of a human body as a specific area from the image information, a histogram generating section 24 that obtains a density histogram from image information and a lookup tale generating section 26 that generates a smoothing lookup table for smoothing the density histograms.
Abstract: PROBLEM TO BE SOLVED: To provide a technology by which gradation of a specific area in an image such as a major object is made proper while utilizing an advantage of density histogram smoothing. SOLUTION: This image processor is provided with an area sensor 6 that reads image information from a negative film, an area extract section 23 that extracts the face of a human body as a specific area from the image information, a histogram generating section 24 that obtains a density histogram from the image information, a lookup tale generating section 26 that generates a smoothing lookup table for smoothing the density histogram, and an image conversion processing section 28 that uses the smoothing lookup table to convert the read image information. Then the image conversion processing is conducted by utilizing advantages of smoothing while keeping the gradation of the face so that a conversion coefficient of the specific area is 1 to 1 in the case of generating the lookup table.
5 citations
Patent•
13 May 2011
TL;DR: In this paper, an object recognition method and a device thereof using an interest area definition and an outline image in an image are presented, where a first preprocessor(4) performs a preprocessing of an image for recognizing a rotated image.
Abstract: PURPOSE: An object recognition method and a device thereof using an interest area definition and an outline image in an image. CONSTITUTION: A first preprocessor(4) performs a preprocessing of an image for recognizing a rotated image. A second preprocessor(5) performs a grey image conversion of an image and a normalization of a size of the outline image. A recognition candidate reducing unit(7) reduces the number of recognizing candidate through a comparison between outline information of an object and an outline information of an image. A recognition unit(8) recognizes an object of the recognizing candidate. A recognizing result confirmation unit(9) checks a recognizing result of the recognized object.
5 citations
Patent•
20 Mar 2002TL;DR: In this paper, a system for generating image conversion data is presented, which includes a numerator buffer storing numerator data of a conversion ratio, such as where the numerator of the ratio represents the relative current size of a set of image data and the denominator of a ratio representing the relative size of the target set of images.
Abstract: A system for generating image conversion data is provided. The system includes a numerator buffer storing numerator data of a conversion ratio, such as where the numerator of the ratio represents the relative current size of a set of image data and the denominator of the ratio represents the relative size of the target set of image data. A denominator buffer stores denominator data of the conversion ratio. A pixel sample control system receives the numerator data and the denominator data and generates pixel sample control data that is used to select a pixel from a pixel data stream, such as to allow a pixel dropping sequence or a pixel duplication sequence to be generated based on the values stored in the numerator buffer and the denominator buffer.
5 citations